CN114791067A - Pipeline robot with heat detection function, control method and control system - Google Patents
Pipeline robot with heat detection function, control method and control system Download PDFInfo
- Publication number
- CN114791067A CN114791067A CN202110099882.1A CN202110099882A CN114791067A CN 114791067 A CN114791067 A CN 114791067A CN 202110099882 A CN202110099882 A CN 202110099882A CN 114791067 A CN114791067 A CN 114791067A
- Authority
- CN
- China
- Prior art keywords
- thermal image
- pipeline
- matrix
- data
- pipeline robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 82
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 6
- 238000010438 heat treatment Methods 0.000 claims abstract description 6
- 238000000513 principal component analysis Methods 0.000 claims description 16
- 239000012530 fluid Substances 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims 2
- 239000000126 substance Substances 0.000 claims 1
- 230000007847 structural defect Effects 0.000 abstract description 8
- 230000000246 remedial effect Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 9
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L55/00—Devices or appurtenances for use in, or in connection with, pipes or pipe systems
- F16L55/26—Pigs or moles, i.e. devices movable in a pipe or conduit with or without self-contained propulsion means
- F16L55/28—Constructional aspects
- F16L55/30—Constructional aspects of the propulsion means, e.g. towed by cables
- F16L55/32—Constructional aspects of the propulsion means, e.g. towed by cables being self-contained
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L2101/00—Uses or applications of pigs or moles
- F16L2101/30—Inspecting, measuring or testing
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention provides a pipeline robot with a thermal detection function, a control method and a control system, which are mainly characterized in that after a pipeline robot body is placed in a pipeline, a flash lamp is used for carrying out pulse heating on the pipeline, meanwhile, a thermal image acquisition unit is used for acquiring a thermal image, the acquired thermal image data is made into two-dimensional thermal image matrix data, singular value decomposition and sparsification are carried out to obtain a sparse principal component load diagram, whether structural defects occur in the pipeline can be obviously known through the sparse principal component load diagram, and therefore, related personnel can immediately carry out remedial measures.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a pipeline robot with a thermal detection function, a control method and a control system.
Background
At present, the pipeline is detected and maintained, or the state in the pipeline is explored, or the sedimentation in the pipeline is cleared up, and most pipeline robots are adopted to complete the process. The detection of the pipeline is mostly done by means of image recognition. However, image recognition can only recognize defects on the inner wall surface of the pipe, and defects on the pipe structure are difficult to recognize, and therefore, the present inventors considered that such problems need to be solved, and began to think about solutions.
Disclosure of Invention
The invention solves the problem that the pipeline robot can only judge the defects on the surface of the pipeline when identifying the defects of the pipeline, and the defects on the structure are difficult to identify.
In order to solve the above problems, the present invention provides a pipeline robot with a thermal detection function, a control method and a control system, wherein the technical scheme is as follows:
when detecting the pipeline, firstly, a flash lamp is used for pulse heating of the pipeline, meanwhile, a thermal image acquisition unit is used for acquiring thermal image acquisition data of the pipeline, then, a thermal image identification unit is used for performing thermal image identification on the thermal image acquisition data, the thermal image acquisition data is firstly made into three-dimensional thermal image matrix data in the identification process, then, the three-dimensional thermal image matrix data is converted into two-dimensional thermal image matrix data, then, the two-dimensional thermal image matrix data is subjected to centering processing to obtain a centering matrix, then, singular value decomposition is performed on the centering matrix to obtain a principal component analysis load matrix, and then, the operation is performed according to the principal component analysis load matrix, when the operation result shows a convergence state, a sparse load matrix is obtained, and when the operation result shows no convergence, the principal components of the principal component analysis load matrix and the principal components of the sparse load matrix are respectively updated.
The principal components of the sparse load matrix are then rearranged into two-dimensional m x *m y Thus, a sparse principal component load map can be obtained. Therefore, a manager can know whether the pipeline has structural defects through the sparse principal component load diagram so as to facilitate subsequent related remedial measures.
Drawings
FIG. 1 is a schematic view of an embodiment of the present invention shown in FIG. 1;
FIG. 2 is a schematic view of an embodiment of the present invention FIG. 2;
FIG. 3 is a schematic view of FIG. 3;
FIG. 4 is a schematic view of the linkage of the components of the present invention;
FIG. 5 is a schematic diagram of the thermal test results of the present invention;
FIG. 6 is a flow chart of the operation of the present invention;
FIG. 7 is a schematic diagram of three-dimensional thermal image matrix data created according to the present invention;
FIG. 8 is a schematic diagram of the two-dimensional thermal image matrix data.
Description of reference numerals:
a-a control center; b-a pipeline; c1-plate; c2-sparse principal component load map; c3-sparse principal component load graph; d-structural defects; 1-a pipeline robot body; 11-tip; 2-a flash lamp; 3-a thermal image capturing unit; 4-a processor; 5-a cylinder pressing unit; 6-a power wheel set; 7-a flow rate detection unit; 8-a positioning unit; 9-thermal image recognition unit.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Referring to fig. 1 to 4, the present invention relates to a pipeline robot with a thermal detection function, a control method and a control system thereof, and the present invention mainly includes:
a pipeline robot body 1, a flash lamp 2, a thermal image capturing unit 3, a processor 4, a pressure cylinder unit 5, a power wheel set 6, a flow rate detecting unit 7, a positioning unit 8, and a thermal image identifying unit 9. A control center A for remotely connecting the pipeline robot body 1, the thermal image recognition unit 9 and the processor 4. Wherein the flash light 2 reaches the thermal image acquisition unit 3 is located the 1 outside of pipeline robot body, power wheelset 6 is located 1 bottom of pipeline robot body the jar unit 5 is located 1 top surface of pipeline robot body.
When the pipeline B is detected, the moving direction of the pipeline robot body 1 from the pipeline to the pipeline B or the working conditions of all components can be controlled through the control center A. Then, during the detection, the flash lamp 2 is controlled to perform the instant pulse heating (about 0.2 seconds) on the inner wall of the pipe B preferably with more than 2000W, so that the temperature of the pipe B rises, and at this time, the thermal image capturing unit 3 needs to be immediately used to capture the pipe B to capture a plurality of thermal image capturing data, wherein the capturing rate of the thermal image capturing unit 3 is about 30 frames/second.
The present invention is mainly improved according to Principal Component Analysis (PCA) for structural defect inspection based on a plurality of thermal image acquisition data. First, please refer to fig. 7, each thermal image capturing data has a plurality of horizontal pixel data and a plurality of vertical pixel data, and the thermal image recognizing unit generates each horizontal pixel data, each vertical pixel data and each thermal image capturing data into a three-dimensional thermal image matrix data n t *n x *n y Wherein n is t Representing the thermal image capture data, n x Representing said horizontal pixel data, n y Representing the vertical pixel data, then referring to FIG. 8, since the three-dimensional data is difficult to observe during data analysis, the three-dimensional thermal image matrix data is then converted into two-dimensional thermal image matrix data n t *n x n y Wherein n is x n y Representing the number of variables.
Then, the two-dimensional thermal image matrix data is subjected to a centering process, in which the thermal image recognition unit 9 calculates an average value according to each variable of the two-dimensional thermal image matrix data, and then subtracts the average value from each variable of the two-dimensional thermal image matrix data to reduce the calculated amount and reduce the influence of uneven heat source, and then a centering matrix X is obtained. Then, Singular Value Decomposition (SVD) is performed on the centering matrix, and the mode is mainly according to the formula: x ═ U ∑ V T And let P be V and set a coefficient value lambda, where P is the principal component analysis load matrix, V load matrix, and the principal component analysis load matrixEach principal component of the matrix is p k ＝[p 1 …p k ]. Where U and V are orthogonal matrices (orthogonal matrices), respectively.
Then, the thermal image recognition unit 9 performs a sparsification process according to the principal component analysis load matrix, mainly according to a formula:
to calculate each principal component q in the sparse load matrix k And simultaneously calculating a sparse load matrix Q.
In the process of obtaining the sparse load matrix, if the sparse load matrix is converged, the thermal image identification unit 9 rearranges the principal components of the sparse load matrix into two-dimensional m x *m y Thus, a sparse principal component load map can be obtained. In this way, the control center a or the manager can know whether the pipeline B has a structural defect through the sparse principal component load graph. It should be noted that the degree of sparsity can be achieved by adjusting the coefficient value λ, and when the degree of sparsity is too low, the coefficient value λ can be increased, whereas when the degree of sparsity is too high, the coefficient value λ can be decreased, so that the degree of sparsity most suitable for observing defects can be obtained by adjusting the coefficient value λ. It should be noted that the coefficient λ may not be 0, and if the coefficient λ is 0, the general Principal Component Analysis (PCA) is performed. In addition, referring to fig. 5, which is a schematic view of a board body C1 with a structural defect D, when a coefficient value λ suitable for observing defects is selected, as shown in the sparse principal component loading map C2, a significant structural defect position is shown, and if the coefficient value λ is set too high, as shown in the sparse principal component loading map C3, a defect position cannot be shown.
In the process of obtaining the sparse load matrix, if the sparse load matrix does not form convergence, the sparsification fails, and at the moment, q needs to be readjusted k And p k The adjustment mode is mainly based on the formula
Q is to be k After unitization, the new p is replaced k The replacement method is according to the formula p k ＝(I－p (k-1) p (k-1) T )X T Xq k To obtain each p k Updating value, p is updated k Then p is aligned again k Unitization is carried out, and the unitization mode is mainly according to a formula:
to achieve this. After all the steps are completed, the above-mentioned sparsifying process procedure is started again. Wherein I represents an identity matrix.
Therefore, the sparse principal component load graph can be quickly and effectively obtained by utilizing the method, so as to know whether the pipeline has structural defects or not. In addition, when the pipeline B is found to have a structural defect, the positioning unit 8 can detect the position of the pipeline robot body 1 to obtain positioning data, the processor 4 can immediately send the positioning data and an alarm signal to the control center a, and the positioning data and the alarm signal are preferably transmitted together with the sparse principal component load diagram during the sending process, so that a manager can know the situation. In addition, the pipeline robot body 1 is preferably provided with a camera, so that the manager can see the conditions in the pipeline B through the camera.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be made by those skilled in the art without departing from the spirit and scope of the disclosure, and these changes and modifications are intended to fall within the scope of the invention.
Claims (10)
1. A pipeline robot with a thermal detection function, comprising:
a pipeline robot body, a flash lamp, a thermal image capturing unit and a thermal image identification unit; wherein the content of the first and second substances,
the pipeline robot body is provided with the flash lamp and the thermal image capturing unit;
the flash lamp is used for pulse heating of the pipeline;
the thermal image capturing unit is used for capturing thermal images of the pipeline while the pulse heating is performed, so that a plurality of thermal image capturing data are obtained;
the thermal image identification unit receives the plurality of thermal image acquisition data from the thermal image acquisition unit; and (c) a second step of,
the thermal image identification unit is used for making each horizontal pixel data, each vertical pixel data and each thermal image acquisition data into three-dimensional thermal image matrix data, and then converting the three-dimensional thermal image matrix data into two-dimensional thermal image matrix data, wherein the two-dimensional thermal image matrix data has a plurality of variables;
the thermal image identification unit calculates an average value according to each variable quantity of the two-dimensional thermal image matrix data, subtracts the average value from each variable quantity of the two-dimensional thermal image matrix data to obtain a centralized matrix, and performs singular value decomposition on the centralized matrix; then, the thermal image identification unit analyzes a load matrix according to the principal component, and calculates a sparse load matrix and the principal component of the sparse load matrix;
when the sparse load matrix is converged, the thermal image identification unit rearranges the principal components of the sparse load matrix into a two-dimensional matrix, and then a sparse principal component load graph can be obtained;
when the sparse load matrix does not form convergence, the thermal image identification unit unitizes principal components of the sparse load matrix, updates each principal component of the principal component analysis load matrix, unitizes each principal component of the principal component analysis load matrix, and calculates the sparse load matrix.
2. The pipeline robot with the function of thermal detection according to claim 1, wherein each thermal image capturing data comprises a plurality of horizontal pixel data and a plurality of vertical pixel data, and the three-dimensional thermal image matrix data is n t *n x *n y Wherein n is t Representing the thermal image capture data, n x Representing said horizontal pixel data, n y Representing the vertical pixel data; the two-dimensional thermal image matrix data n t *n x n y Wherein n is x n y Represents the number of variables;
the thermal image identification unit is according to the formula: x ═ U ∑ V T Performing singular value decomposition on the centering matrix, setting P as V and setting a coefficient value lambda, wherein P is a principal component analysis load matrix and V is a load matrix, and each principal component of the principal component analysis load matrix is P k ＝[p 1 …p k ]；
The thermal image identification unit calculates the sparse load matrix Q and the principal component Q of the sparse load matrix k According to the formula:
the thermal shadow is formed when the sparse load matrix convergesThe image recognition unit rearranges the principal components of the sparse load matrix into two-dimensional m x *m y Obtaining a sparse principal component load graph;
the thermal image identification unit is based on a formula
Unitizing and then according to the formula p k ＝(I－p (k-1) p (k-1) T )X T Xq k To p is p k Updating is performed, after which, according to the formula:
to p is p k And calculating the sparse load matrix after unitization.
3. The pipeline robot with the heat detection function according to claim 2,
the top surface of the pipeline robot body is provided with a pressure cylinder unit, and the pressure cylinder unit is provided with a pressure cylinder rod;
a processor is arranged in the pipeline robot body, and the processor is in information connection with the pressure cylinder unit;
the processor is used for generating a control signal, and the pressure cylinder unit controls the pressure cylinder rod to extend outwards to prop against the top wall of the pipeline or controls the pressure cylinder rod to be far away from the top wall of the pipeline according to the control signal.
4. The pipeline robot with the function of heat detection according to claim 3, wherein a power wheel set is provided at the bottom of the pipeline robot body for driving the pipeline robot body to move;
the pipeline robot body is provided with a flow velocity detection unit;
the flow velocity detection unit is in information connection with the processor and is used for detecting the flow velocity of the fluid in the pipeline to obtain a flow velocity detection result and uploading the flow velocity detection result to the processor;
and when the processor judges that the flow rate detection result exceeds a default value, the processor immediately generates the control signal, and the pressure cylinder unit controls the pressure cylinder rod to jack the top wall of the pipeline according to the control signal and controls the power wheel set to stop working.
5. The pipeline robot with heat detecting function as claimed in claim 4, wherein the pipeline robot body is provided with a positioning unit for detecting the position of the pipeline robot body to obtain a positioning data, the processor is used for connecting a control center via remote information, and when the processor determines that the pipe wall of the pipeline is defective according to the sparse principal component load diagram, the processor immediately sends an alarm signal and the positioning data to the control center.
6. A control method of a pipeline robot having a thermal detection function, applied to the pipeline robot of any one of claims 1 to 5, comprising: a pipeline robot body, a flash lamp, a thermal image capturing unit and a thermal image identification unit; the control method comprises the following steps:
(A) the pipeline robot body utilizes the flash lamp to perform pulse heating on the pipeline in the pipeline, and simultaneously controls the thermal image acquisition unit to perform thermal image acquisition on the pipeline to obtain a plurality of thermal image acquisition data, wherein each thermal image acquisition data comprises a plurality of horizontal pixel data and a plurality of vertical pixel data;
(B) the thermal image identification unit makes each horizontal pixel data, each vertical pixel data and each thermal image acquisition data into a three-dimensional thermal image matrix data n t *n x *n y Wherein n is t Representing the thermal image capture data, n x Representing said horizontal pixel data, n y Representing the vertical pixel data, and converting the three-dimensional thermal image matrix data into two-dimensional thermal image matrix data n t *n x n y Wherein n is x n y Represents the number of variables;
(C) the thermal image identification unit calculates an average value according to each variable quantity of the two-dimensional thermal image matrix data, subtracts the average value from each variable quantity of the two-dimensional thermal image matrix data to obtain a centralized matrix X, and then obtains a thermal image matrix X according to a formula: x ═ U ∑ V T Performing singular value decomposition on the centering matrix, setting P as V and setting a coefficient value lambda, wherein P is a principal component analysis load matrix and V is a load matrix, and each principal component of the principal component analysis load matrix is P k ＝[p 1 …p k ]；
(D) The thermal image identification unit analyzes a load matrix and a formula according to the principal component:
calculating a sparse load matrix Q and a principal component Q of the sparse load matrix k ；
(E) Performing step (F) when the sparse load matrix forms convergence, and performing step (G) when the sparse load matrix does not form convergence;
(F) the thermal image identification unit rearranges the principal components of the sparse load matrix into two-dimensional m x *m y Obtaining a sparse principal component load graph;
(G) the thermal image identification unit will identify the thermal image according to the formula
Q is to be k Unitization is carried out; then according to the formula p k ＝(I－p (k-1) p (k-1) T )X T Xq k To p k Updating is performed, and then according to the formula:
to p is p k After unitization, step (D) is performed.
7. The method for controlling a pipeline robot having a heat detection function according to claim 6, wherein the pipeline robot comprises: a power wheel set and a pressure cylinder unit; further comprising the step (H): after receiving the instruction, the processor in the pipeline robot can control the power wheel set to work or control the pressure cylinder unit to work, and will press the cylinder rod of the pressure cylinder unit to extend outwards and withstand the pipeline top wall, or control the pressure cylinder rod is kept away from the pipeline top wall.
8. The method for controlling a pipeline robot having a thermal detection function according to claim 7, further comprising the step (I): when the flow velocity detecting unit of the pipeline robot body detects that the fluid velocity in the pipeline exceeds a default value, the power wheel set stops working immediately, and meanwhile, the pressure cylinder rod immediately props against the top wall of the pipeline.
9. The method of controlling a pipeline robot having a thermal detection function according to claim 8, wherein the pipeline robot comprises: a positioning unit; further comprising the step (J): the positioning unit can be used for detecting the position of the pipeline robot body to obtain positioning data, the processor can be used for connecting remote information with a control center, and when the processor judges that the pipe wall of the pipeline is defective according to the sparse principal component load diagram, an alarm signal and the positioning data are immediately sent to the control center.
10. A robot control system, comprising:
the pipeline robot of any one of claims 1-5;
a control center, wherein the control center is connected to the pipeline robot in an information mode;
the control center controls the pipeline robot according to the control method of any one of the above claims 6 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110099882.1A CN114791067B (en) | 2021-01-25 | 2021-01-25 | Pipeline robot with heat detection function, control method and control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110099882.1A CN114791067B (en) | 2021-01-25 | 2021-01-25 | Pipeline robot with heat detection function, control method and control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114791067A true CN114791067A (en) | 2022-07-26 |
| CN114791067B CN114791067B (en) | 2024-02-06 |
Family
ID=82460738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110099882.1A Active CN114791067B (en) | 2021-01-25 | 2021-01-25 | Pipeline robot with heat detection function, control method and control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114791067B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004053659A2 (en) * | 2002-12-10 | 2004-06-24 | Stone Investments, Inc | Method and system for analyzing data and creating predictive models |
| JP2005300179A (en) * | 2004-04-06 | 2005-10-27 | Constec Engi Co | Infrared structure diagnosis system |
| KR100816018B1 (en) * | 2007-01-19 | 2008-03-21 | 한국과학기술원 | Method for super-resolution reconstruction using focal underdetermined system solver algorithm |
| CN102565081A (en) * | 2012-01-12 | 2012-07-11 | 北京化工大学 | Method for detecting pipeline defects based on three-dimensional data points acquired through circle structured light vision detection |
| CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
| JP2013250098A (en) * | 2012-05-30 | 2013-12-12 | Sharp Corp | Method and apparatus for detecting wiring defect, and method for manufacturing wiring board |
| CN104833699A (en) * | 2015-04-21 | 2015-08-12 | 电子科技大学 | Greedy sparse decomposition-based ECPT defect rapid detection method |
| WO2016162930A1 (en) * | 2015-04-06 | 2016-10-13 | 三菱電機株式会社 | Nondestructive inspection system and singularity detection system |
| JP2017060965A (en) * | 2015-09-25 | 2017-03-30 | Ｊｆｅスチール株式会社 | Surface defect judgment method and apparatus for continuous casting piece and billet manufacturing method using surface defect judgment method |
| CN107909653A (en) * | 2017-11-15 | 2018-04-13 | 电子科技大学 | A kind of heart soft tissue three-dimensional rebuilding method based on sparse principal component analysis |
| US10089734B1 (en) * | 2018-01-21 | 2018-10-02 | Meir Gershenson | Equivalent wave field processing of thermal images |
| CN108680602A (en) * | 2018-05-18 | 2018-10-19 | 云南电网有限责任公司电力科学研究院 | A kind of detection device, the method and system of porcelain insulator internal flaw |
| CN109885027A (en) * | 2019-03-13 | 2019-06-14 | 东北大学 | Industrial process method for diagnosing faults based on the sparse orthogonal discriminant analysis of bidirectional two-dimensional |
| CN110108754A (en) * | 2019-04-25 | 2019-08-09 | 四川沐迪圣科技有限公司 | The light stimulus infrared thermal imaging defect inspection method decomposed based on structural sparse |
| CN110159869A (en) * | 2019-05-20 | 2019-08-23 | 山东大学 | A kind of detecting robot of pipe and its Multi-sensor Fusion detection method |
| US10504230B1 (en) * | 2014-12-19 | 2019-12-10 | Amazon Technologies, Inc. | Machine vision calibration system with marker |
| CN211315502U (en) * | 2019-12-18 | 2020-08-21 | 杭州申昊科技股份有限公司 | Lifting cradle head detection mechanism and pipeline robot with same |
| CN211694003U (en) * | 2019-12-18 | 2020-10-16 | 杭州申昊科技股份有限公司 | Detection control system of pipeline robot |
| CN112229900A (en) * | 2020-10-28 | 2021-01-15 | 中国计量大学 | Flexible intelligent pipeline defect detection device |
-
2021
- 2021-01-25 CN CN202110099882.1A patent/CN114791067B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004053659A2 (en) * | 2002-12-10 | 2004-06-24 | Stone Investments, Inc | Method and system for analyzing data and creating predictive models |
| JP2005300179A (en) * | 2004-04-06 | 2005-10-27 | Constec Engi Co | Infrared structure diagnosis system |
| KR100816018B1 (en) * | 2007-01-19 | 2008-03-21 | 한국과학기술원 | Method for super-resolution reconstruction using focal underdetermined system solver algorithm |
| CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
| CN102565081A (en) * | 2012-01-12 | 2012-07-11 | 北京化工大学 | Method for detecting pipeline defects based on three-dimensional data points acquired through circle structured light vision detection |
| JP2013250098A (en) * | 2012-05-30 | 2013-12-12 | Sharp Corp | Method and apparatus for detecting wiring defect, and method for manufacturing wiring board |
| US10504230B1 (en) * | 2014-12-19 | 2019-12-10 | Amazon Technologies, Inc. | Machine vision calibration system with marker |
| WO2016162930A1 (en) * | 2015-04-06 | 2016-10-13 | 三菱電機株式会社 | Nondestructive inspection system and singularity detection system |
| CN104833699A (en) * | 2015-04-21 | 2015-08-12 | 电子科技大学 | Greedy sparse decomposition-based ECPT defect rapid detection method |
| JP2017060965A (en) * | 2015-09-25 | 2017-03-30 | Ｊｆｅスチール株式会社 | Surface defect judgment method and apparatus for continuous casting piece and billet manufacturing method using surface defect judgment method |
| CN107909653A (en) * | 2017-11-15 | 2018-04-13 | 电子科技大学 | A kind of heart soft tissue three-dimensional rebuilding method based on sparse principal component analysis |
| US10089734B1 (en) * | 2018-01-21 | 2018-10-02 | Meir Gershenson | Equivalent wave field processing of thermal images |
| CN108680602A (en) * | 2018-05-18 | 2018-10-19 | 云南电网有限责任公司电力科学研究院 | A kind of detection device, the method and system of porcelain insulator internal flaw |
| CN109885027A (en) * | 2019-03-13 | 2019-06-14 | 东北大学 | Industrial process method for diagnosing faults based on the sparse orthogonal discriminant analysis of bidirectional two-dimensional |
| CN110108754A (en) * | 2019-04-25 | 2019-08-09 | 四川沐迪圣科技有限公司 | The light stimulus infrared thermal imaging defect inspection method decomposed based on structural sparse |
| CN110159869A (en) * | 2019-05-20 | 2019-08-23 | 山东大学 | A kind of detecting robot of pipe and its Multi-sensor Fusion detection method |
| CN211315502U (en) * | 2019-12-18 | 2020-08-21 | 杭州申昊科技股份有限公司 | Lifting cradle head detection mechanism and pipeline robot with same |
| CN211694003U (en) * | 2019-12-18 | 2020-10-16 | 杭州申昊科技股份有限公司 | Detection control system of pipeline robot |
| CN112229900A (en) * | 2020-10-28 | 2021-01-15 | 中国计量大学 | Flexible intelligent pipeline defect detection device |
Non-Patent Citations (7)
| Title |
|---|
| 张峻宁;张培林;华春蓉;李兵;陈彦龙;: "引入稀疏原子特征融合的滑动轴承摩擦故障状态监测", no. 10 * |
| 彭必灿, 张正道: "基于稀疏主元分析的过程监控研究", 《计算机工程与应用》, pages 243 * |
| 朱新峰;田叶;徐琴;: "光谱学中的稀疏化方法", no. 08 * |
| 熊小芸;宋朝晖;季飞;马惠珠;: "基金项目智能受理相关问题――申请代码、研究方向与关键词" * |
| 王振宇;秦立龙;刁俊良;: "基于K-SVD和稀疏表示的数字调制模式识别", no. 10 * |
| 王磊;聂晖;: "基于稀疏主成分的空调***传感器故障诊断", no. 09 * |
| 顾强;: "分类降维法在电信终端产品评分中的应用", no. 16 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114791067B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102037893B1 (en) | System and method for establishing digital exterior survey map | |
| CN105716539B (en) | A kind of three-dimentioned shape measurement method of quick high accuracy | |
| KR20190142626A (en) | System and method for autonomous crack evaluation of structure using hybrid image scanning | |
| CN108581869B (en) | Camera module alignment method | |
| DE102012021375A1 (en) | Apparatus and method for detecting a three-dimensional position and orientation of an article | |
| CN112548516B (en) | Vision-based spline automatic assembly system and method | |
| CN111157539B (en) | Weld morphology monitoring method, system and device and readable storage medium | |
| CN110560376B (en) | Product surface defect detection method and device | |
| CN111768417B (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
| CN113276106A (en) | Climbing robot space positioning method and space positioning system | |
| CN110146029B (en) | Quasi-static full-field deformation measuring device and method for slender component | |
| CN113762240A (en) | Method and system for predicting geometrical characteristics of cladding layer based on deep learning | |
| KR102559586B1 (en) | Structural appearance inspection system and method using artificial intelligence | |
| CN113902698A (en) | Unmanned aerial vehicle holder progressive target focusing method based on intelligent visual control | |
| CN114193440B (en) | Robot automatic grabbing system and method based on 3D vision | |
| CN114791067A (en) | Pipeline robot with heat detection function, control method and control system | |
| US20200221055A1 (en) | Systems and methods for compression and recovery of data in additive manufacturing applications | |
| CN108871238B (en) | Method and device for measuring straightness of zirconium tube for nuclear power | |
| KR101236845B1 (en) | System for measuring an object and method for measuring an object using the same | |
| CN113295732B (en) | Pipeline robot capable of detecting pipeline defects and control method and control system thereof | |
| CN107607539B (en) | Connecting rod expansion section quality visual detection device and detection method | |
| CN106595502A (en) | Structured light-based motion compensation 3D measurement method | |
| CN110977292A (en) | Automatic detection method for welding seam of ocean platform module structure | |
| CN212965178U (en) | Device for rapidly measuring electric field noise on metal surface | |
| CN109435226B (en) | Large-range 3D printing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |